{"id":"https://openalex.org/W4386763799","doi":"https://doi.org/10.1109/waspaa58266.2023.10248146","title":"Directional Target Speaker Extraction under Noisy Underdetermined Conditions through Conditional Variational Autoencoder with Global Style Tokens","display_name":"Directional Target Speaker Extraction under Noisy Underdetermined Conditions through Conditional Variational Autoencoder with Global Style Tokens","publication_year":2023,"publication_date":"2023-09-15","ids":{"openalex":"https://openalex.org/W4386763799","doi":"https://doi.org/10.1109/waspaa58266.2023.10248146"},"language":"en","primary_location":{"id":"doi:10.1109/waspaa58266.2023.10248146","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/waspaa58266.2023.10248146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"},"type":"conference-paper","indexed_in":["crossref"],"open_access":{"is_oa":false,"oa_status":"closed","oa_url":null,"any_repository_has_fulltext":false},"authorships":[{"author_position":"first","author":{"id":"https://openalex.org/A5100431295","display_name":"Rui Wang","orcid":"https://orcid.org/0000-0002-6719-5071"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Rui Wang","raw_affiliation_strings":["Nagoya University,Graduate School of Informatics","Graduate School of Informatics, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Graduate School of Informatics","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Graduate School of Informatics, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]},{"author_position":"last","author":{"id":"https://openalex.org/A5078330211","display_name":"Tomoki Toda","orcid":"https://orcid.org/0000-0001-8146-1279"},"institutions":[{"id":"https://openalex.org/I60134161","display_name":"Nagoya University","ror":"https://ror.org/04chrp450","country_code":"JP","type":"education","lineage":["https://openalex.org/I60134161"]}],"countries":["JP"],"is_corresponding":false,"raw_author_name":"Tomoki Toda","raw_affiliation_strings":["Nagoya University,Information Technology Center","Information Technology Center, Nagoya University"],"raw_orcid":null,"affiliations":[{"raw_affiliation_string":"Nagoya University,Information Technology Center","institution_ids":["https://openalex.org/I60134161"]},{"raw_affiliation_string":"Information Technology Center, Nagoya University","institution_ids":["https://openalex.org/I60134161"]}]}],"institutions":[],"countries_distinct_count":1,"institutions_distinct_count":1,"corresponding_author_ids":[],"corresponding_institution_ids":["https://openalex.org/I60134161"],"apc_list":null,"apc_paid":null,"fwci":null,"has_fulltext":false,"cited_by_count":0,"citation_normalized_percentile":null,"cited_by_percentile_year":null,"biblio":{"volume":"117","issue":null,"first_page":"1","last_page":"5"},"is_retracted":false,"is_paratext":false,"is_xpac":false,"primary_topic":{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},"topics":[{"id":"https://openalex.org/T10860","display_name":"Speech and Audio Processing","score":1.0,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T11309","display_name":"Music and Audio Processing","score":0.9991999864578247,"subfield":{"id":"https://openalex.org/subfields/1711","display_name":"Signal Processing"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}},{"id":"https://openalex.org/T10201","display_name":"Speech Recognition and Synthesis","score":0.9987000226974487,"subfield":{"id":"https://openalex.org/subfields/1702","display_name":"Artificial Intelligence"},"field":{"id":"https://openalex.org/fields/17","display_name":"Computer Science"},"domain":{"id":"https://openalex.org/domains/3","display_name":"Physical Sciences"}}],"keywords":[{"id":"https://openalex.org/keywords/underdetermined-system","display_name":"Underdetermined system","score":0.9703892469406128},{"id":"https://openalex.org/keywords/computer-science","display_name":"Computer science","score":0.7347697615623474},{"id":"https://openalex.org/keywords/autoencoder","display_name":"Autoencoder","score":0.6716099977493286},{"id":"https://openalex.org/keywords/constraint","display_name":"Constraint (computer-aided design)","score":0.6613656282424927},{"id":"https://openalex.org/keywords/noise","display_name":"Noise (video)","score":0.6250852346420288},{"id":"https://openalex.org/keywords/speech-recognition","display_name":"Speech recognition","score":0.4661817252635956},{"id":"https://openalex.org/keywords/channel","display_name":"Channel (broadcasting)","score":0.45783567428588867},{"id":"https://openalex.org/keywords/artificial-intelligence","display_name":"Artificial intelligence","score":0.440208375453949},{"id":"https://openalex.org/keywords/source-separation","display_name":"Source separation","score":0.43100452423095703},{"id":"https://openalex.org/keywords/pattern-recognition","display_name":"Pattern recognition (psychology)","score":0.4036015272140503},{"id":"https://openalex.org/keywords/algorithm","display_name":"Algorithm","score":0.3037574291229248},{"id":"https://openalex.org/keywords/artificial-neural-network","display_name":"Artificial neural network","score":0.24129921197891235},{"id":"https://openalex.org/keywords/image","display_name":"Image (mathematics)","score":0.17157122492790222},{"id":"https://openalex.org/keywords/mathematics","display_name":"Mathematics","score":0.1636972725391388}],"concepts":[{"id":"https://openalex.org/C179690561","wikidata":"https://www.wikidata.org/wiki/Q4316110","display_name":"Underdetermined system","level":2,"score":0.9703892469406128},{"id":"https://openalex.org/C41008148","wikidata":"https://www.wikidata.org/wiki/Q21198","display_name":"Computer science","level":0,"score":0.7347697615623474},{"id":"https://openalex.org/C101738243","wikidata":"https://www.wikidata.org/wiki/Q786435","display_name":"Autoencoder","level":3,"score":0.6716099977493286},{"id":"https://openalex.org/C2776036281","wikidata":"https://www.wikidata.org/wiki/Q48769818","display_name":"Constraint (computer-aided design)","level":2,"score":0.6613656282424927},{"id":"https://openalex.org/C99498987","wikidata":"https://www.wikidata.org/wiki/Q2210247","display_name":"Noise (video)","level":3,"score":0.6250852346420288},{"id":"https://openalex.org/C28490314","wikidata":"https://www.wikidata.org/wiki/Q189436","display_name":"Speech recognition","level":1,"score":0.4661817252635956},{"id":"https://openalex.org/C127162648","wikidata":"https://www.wikidata.org/wiki/Q16858953","display_name":"Channel (broadcasting)","level":2,"score":0.45783567428588867},{"id":"https://openalex.org/C154945302","wikidata":"https://www.wikidata.org/wiki/Q11660","display_name":"Artificial intelligence","level":1,"score":0.440208375453949},{"id":"https://openalex.org/C2776864781","wikidata":"https://www.wikidata.org/wiki/Q52617913","display_name":"Source separation","level":2,"score":0.43100452423095703},{"id":"https://openalex.org/C153180895","wikidata":"https://www.wikidata.org/wiki/Q7148389","display_name":"Pattern recognition (psychology)","level":2,"score":0.4036015272140503},{"id":"https://openalex.org/C11413529","wikidata":"https://www.wikidata.org/wiki/Q8366","display_name":"Algorithm","level":1,"score":0.3037574291229248},{"id":"https://openalex.org/C50644808","wikidata":"https://www.wikidata.org/wiki/Q192776","display_name":"Artificial neural network","level":2,"score":0.24129921197891235},{"id":"https://openalex.org/C115961682","wikidata":"https://www.wikidata.org/wiki/Q860623","display_name":"Image (mathematics)","level":2,"score":0.17157122492790222},{"id":"https://openalex.org/C33923547","wikidata":"https://www.wikidata.org/wiki/Q395","display_name":"Mathematics","level":0,"score":0.1636972725391388},{"id":"https://openalex.org/C31258907","wikidata":"https://www.wikidata.org/wiki/Q1301371","display_name":"Computer network","level":1,"score":0.0},{"id":"https://openalex.org/C2524010","wikidata":"https://www.wikidata.org/wiki/Q8087","display_name":"Geometry","level":1,"score":0.0}],"mesh":[],"locations_count":1,"locations":[{"id":"doi:10.1109/waspaa58266.2023.10248146","is_oa":false,"landing_page_url":"http://dx.doi.org/10.1109/waspaa58266.2023.10248146","pdf_url":null,"source":null,"license":null,"license_id":null,"version":"publishedVersion","is_accepted":true,"is_published":true,"raw_source_name":"2023 IEEE Workshop on Applications of Signal Processing to Audio and Acoustics (WASPAA)","raw_type":"proceedings-article"}],"best_oa_location":null,"sustainable_development_goals":[],"awards":[],"funders":[],"has_content":{"grobid_xml":false,"pdf":false},"content_urls":null,"referenced_works_count":34,"referenced_works":["https://openalex.org/W1845880232","https://openalex.org/W1887941968","https://openalex.org/W2013096382","https://openalex.org/W2024490156","https://openalex.org/W2072548008","https://openalex.org/W2108501770","https://openalex.org/W2113145093","https://openalex.org/W2117678320","https://openalex.org/W2134910060","https://openalex.org/W2139302694","https://openalex.org/W2155112232","https://openalex.org/W2161270956","https://openalex.org/W2170140777","https://openalex.org/W2400273387","https://openalex.org/W2408744528","https://openalex.org/W2412956798","https://openalex.org/W2789934054","https://openalex.org/W2794490148","https://openalex.org/W2804576393","https://openalex.org/W2808718747","https://openalex.org/W2962866211","https://openalex.org/W2963375116","https://openalex.org/W3000508686","https://openalex.org/W3015233996","https://openalex.org/W3209141406","https://openalex.org/W4226115251","https://openalex.org/W4253928870","https://openalex.org/W4312069036","https://openalex.org/W6675944832","https://openalex.org/W6750489868","https://openalex.org/W6775557461","https://openalex.org/W6802983977","https://openalex.org/W6810827206","https://openalex.org/W6981753326"],"related_works":["https://openalex.org/W2594498979","https://openalex.org/W2982840733","https://openalex.org/W2139141473","https://openalex.org/W2989942677","https://openalex.org/W2894192904","https://openalex.org/W1887941968","https://openalex.org/W3163618433","https://openalex.org/W2315900886","https://openalex.org/W2113403277","https://openalex.org/W2047629616"],"abstract_inverted_index":{"This":[0,57],"paper":[1,76],"proposes":[2],"a":[3,83,121,125],"dual-channel":[4,122],"target":[5],"speaker":[6],"extraction":[7],"(TSE)":[8],"method":[9],"that":[10],"is":[11,55,58,117],"direction-aware":[12],"and":[13,52,98,105],"works":[14],"effectively":[15],"under":[16,146],"noisy":[17,35,89,147],"underdetermined":[18,36,148],"conditions.":[19,149],"While":[20],"the":[21,43,48,61,64,109,131,134,142],"geometric":[22,126],"source":[23,65,110],"separation":[24],"(GSS)":[25],"framework":[26,123],"has":[27],"shown":[28],"effectiveness":[29,132],"in":[30,38,67,120,141],"TSE,":[31],"it":[32],"struggles":[33],"with":[34,92,100,124],"conditions":[37],"many":[39],"realistic":[40],"scenarios,":[41],"where":[42],"number":[44,49],"of":[45,50,63,103,133,144],"speakers":[46,104],"exceeds":[47],"microphones":[51],"diffuse":[53],"noise":[54,106],"present.":[56],"due":[59],"to":[60,87],"limitation":[62],"model":[66,88,111],"traditional":[68],"GSS":[69],"methods.":[70],"To":[71],"address":[72],"this":[73,75],"challenge,":[74],"introduces":[77],"global":[78],"style":[79],"tokens":[80],"(GST)":[81],"within":[82],"variational":[84],"autoencoding":[85],"(CVAE)":[86],"mixed":[90],"speech":[91],"multi-speakers.":[93],"We":[94],"jointly":[95],"train":[96],"GST":[97],"CVAE":[99],"varying":[101],"numbers":[102],"environments":[107],"as":[108],"for":[112],"an":[113],"interference":[114],"mixture,":[115],"which":[116],"then":[118],"applied":[119],"constraint.":[127],"Experimental":[128],"results":[129],"demonstrate":[130],"proposed":[135],"GST-CVAE":[136],"architecture":[137],"achieving":[138],"significant":[139],"improvement":[140],"performance":[143],"TSE":[145]},"counts_by_year":[],"updated_date":"2026-07-14T23:27:15.235271","created_date":"2025-10-10T00:00:00"}